File size: 15,922 Bytes
92cb222 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
{
"results": {
"quasi-numquam-7648_logiqa2_base": {
"alias": "quasi-numquam-7648_logiqa2_base",
"acc,none": 0.33078880407124683,
"acc_stderr,none": 0.011870497134083655
},
"quasi-numquam-7648_logiqa_base": {
"alias": "quasi-numquam-7648_logiqa_base",
"acc,none": 0.305111821086262,
"acc_stderr,none": 0.01841819090875921
},
"quasi-numquam-7648_lsat-ar_base": {
"alias": "quasi-numquam-7648_lsat-ar_base",
"acc,none": 0.20869565217391303,
"acc_stderr,none": 0.026854108265439658
},
"quasi-numquam-7648_lsat-lr_base": {
"alias": "quasi-numquam-7648_lsat-lr_base",
"acc,none": 0.2803921568627451,
"acc_stderr,none": 0.019910033171474106
},
"quasi-numquam-7648_lsat-rc_base": {
"alias": "quasi-numquam-7648_lsat-rc_base",
"acc,none": 0.31970260223048325,
"acc_stderr,none": 0.02848754954266944
}
},
"group_subtasks": {
"quasi-numquam-7648_logiqa2_base": [],
"quasi-numquam-7648_logiqa_base": [],
"quasi-numquam-7648_lsat-ar_base": [],
"quasi-numquam-7648_lsat-lr_base": [],
"quasi-numquam-7648_lsat-rc_base": []
},
"configs": {
"quasi-numquam-7648_logiqa2_base": {
"task": "quasi-numquam-7648_logiqa2_base",
"tag": "logikon-bench",
"group": "logikon-bench",
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
"dataset_kwargs": {
"data_files": {
"test": "data/meta-llama/Llama-3.2-3B-Instruct/quasi-numquam-7648-logiqa2.parquet"
}
},
"test_split": "test",
"doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n",
"doc_to_target": "{{answer}}",
"doc_to_choice": "{{options}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"quasi-numquam-7648_logiqa_base": {
"task": "quasi-numquam-7648_logiqa_base",
"tag": "logikon-bench",
"group": "logikon-bench",
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
"dataset_kwargs": {
"data_files": {
"test": "data/meta-llama/Llama-3.2-3B-Instruct/quasi-numquam-7648-logiqa.parquet"
}
},
"test_split": "test",
"doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n",
"doc_to_target": "{{answer}}",
"doc_to_choice": "{{options}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"quasi-numquam-7648_lsat-ar_base": {
"task": "quasi-numquam-7648_lsat-ar_base",
"tag": "logikon-bench",
"group": "logikon-bench",
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
"dataset_kwargs": {
"data_files": {
"test": "data/meta-llama/Llama-3.2-3B-Instruct/quasi-numquam-7648-lsat-ar.parquet"
}
},
"test_split": "test",
"doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n",
"doc_to_target": "{{answer}}",
"doc_to_choice": "{{options}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"quasi-numquam-7648_lsat-lr_base": {
"task": "quasi-numquam-7648_lsat-lr_base",
"tag": "logikon-bench",
"group": "logikon-bench",
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
"dataset_kwargs": {
"data_files": {
"test": "data/meta-llama/Llama-3.2-3B-Instruct/quasi-numquam-7648-lsat-lr.parquet"
}
},
"test_split": "test",
"doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n",
"doc_to_target": "{{answer}}",
"doc_to_choice": "{{options}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"quasi-numquam-7648_lsat-rc_base": {
"task": "quasi-numquam-7648_lsat-rc_base",
"tag": "logikon-bench",
"group": "logikon-bench",
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
"dataset_kwargs": {
"data_files": {
"test": "data/meta-llama/Llama-3.2-3B-Instruct/quasi-numquam-7648-lsat-rc.parquet"
}
},
"test_split": "test",
"doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n",
"doc_to_target": "{{answer}}",
"doc_to_choice": "{{options}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
}
},
"versions": {
"quasi-numquam-7648_logiqa2_base": 0.0,
"quasi-numquam-7648_logiqa_base": 0.0,
"quasi-numquam-7648_lsat-ar_base": 0.0,
"quasi-numquam-7648_lsat-lr_base": 0.0,
"quasi-numquam-7648_lsat-rc_base": 0.0
},
"n-shot": {
"quasi-numquam-7648_logiqa2_base": 0,
"quasi-numquam-7648_logiqa_base": 0,
"quasi-numquam-7648_lsat-ar_base": 0,
"quasi-numquam-7648_lsat-lr_base": 0,
"quasi-numquam-7648_lsat-rc_base": 0
},
"higher_is_better": {
"quasi-numquam-7648_logiqa2_base": {
"acc": true
},
"quasi-numquam-7648_logiqa_base": {
"acc": true
},
"quasi-numquam-7648_lsat-ar_base": {
"acc": true
},
"quasi-numquam-7648_lsat-lr_base": {
"acc": true
},
"quasi-numquam-7648_lsat-rc_base": {
"acc": true
}
},
"n-samples": {
"quasi-numquam-7648_lsat-rc_base": {
"original": 269,
"effective": 269
},
"quasi-numquam-7648_lsat-lr_base": {
"original": 510,
"effective": 510
},
"quasi-numquam-7648_lsat-ar_base": {
"original": 230,
"effective": 230
},
"quasi-numquam-7648_logiqa_base": {
"original": 626,
"effective": 626
},
"quasi-numquam-7648_logiqa2_base": {
"original": 1572,
"effective": 1572
}
},
"config": {
"model": "local-completions",
"model_args": "base_url=http://localhost:8080/v1/completions,num_concurrent=1,max_retries=3,tokenized_requests=False,model=meta-llama/Llama-3.2-3B-Instruct",
"batch_size": "1",
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "fc673dc",
"date": 1727435026.109854,
"pretty_env_info": "PyTorch version: 2.4.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Red Hat Enterprise Linux release 8.8 (Ootpa) (x86_64)\nGCC version: (GCC) 8.5.0 20210514 (Red Hat 8.5.0-18)\nClang version: Could not collect\nCMake version: version 3.20.2\nLibc version: glibc-2.28\n\nPython version: 3.11.2 (main, May 20 2024, 08:58:58) [GCC 8.5.0 20210514 (Red Hat 8.5.0-18)] (64-bit runtime)\nPython platform: Linux-4.18.0-477.70.1.el8_8.x86_64-x86_64-with-glibc2.28\nIs CUDA available: True\nCUDA runtime version: 12.2.140\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: NVIDIA A100-SXM4-40GB\nNvidia driver version: 550.54.15\ncuDNN version: Probably one of the following:\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_adv_train.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_ops_train.so.8.1.1\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitektur: x86_64\nCPU Operationsmodus: 32-bit, 64-bit\nByte-Reihenfolge: Little Endian\nCPU(s): 152\nListe der Online-CPU(s): 0-151\nThread(s) pro Kern: 2\nKern(e) pro Socket: 38\nSockel: 2\nNUMA-Knoten: 2\nAnbieterkennung: GenuineIntel\nProzessorfamilie: 6\nModell: 106\nModellname: Intel(R) Xeon(R) Platinum 8368 CPU @ 2.40GHz\nStepping: 6\nCPU MHz: 2400.000\nMaximale Taktfrequenz der CPU: 3400,0000\nMinimale Taktfrequenz der CPU: 800,0000\nBogoMIPS: 4800.00\nVirtualisierung: VT-x\nL1d Cache: 48K\nL1i Cache: 32K\nL2 Cache: 1280K\nL3 Cache: 58368K\nNUMA-Knoten0 CPU(s): 0-37,76-113\nNUMA-Knoten1 CPU(s): 38-75,114-151\nMarkierungen: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.4.1\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.45.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|eot_id|>",
"128009"
],
"tokenizer_eos_token": [
"<|eot_id|>",
"128009"
],
"tokenizer_bos_token": [
"<|begin_of_text|>",
"128000"
],
"eot_token_id": 128009,
"max_length": 2047,
"task_hashes": {},
"model_source": "local-completions",
"model_name": "meta-llama/Llama-3.2-3B-Instruct",
"model_name_sanitized": "meta-llama__Llama-3.2-3B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 246661.741766795,
"end_time": 247197.018514625,
"total_evaluation_time_seconds": "535.2767478300084"
} |